© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13679
    Prev
    Next
    INDEX
    Explanations

    Beyoncé, Jolie, oncé

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aldehydes
    0.60
    ᱙
    0.60
     bhikkhave
    0.60
     понимать
    0.60
    ເປັນ
    0.57
    ᆢ
    0.57
     eutectic
    0.56
     centrifugal
    0.55
     hypoxia
    0.54
    🧉
    0.54
    POSITIVE LOGITS
    كلم
    0.58
     Festival
    0.55
     Interviews
    0.54
     يول
    0.51
    פת
    0.49
    <strong>
    0.49
    Circ
    0.48
    ك
    0.48
    пла
    0.46
    }\|
    0.46
    Activations Density 0.001%

    No Known Activations